Databricks introduces ai_search() SQL function for RAG pipelines (Beta)
Databricks has launched the `ai_search()` SQL function in Beta, designed to retrieve and process information from AI Search indexes configured as knowledge sources. This function optimizes search queries, deduplicates results, reranks them by relevance, and can synthesize grounded natural-language answers. It enables users to enrich operational data, build batch retrieval-augmented generation (RAG) pipelines, or integrate retrieval into compound AI systems. The feature is currently available in Beta.
Features (1) ›
- New ai_search() SQL function for enhanced data retrieval
The `ai_search()` SQL function, now in Beta, allows users to retrieve information from one or more configured AI Search indexes. It processes natural-language queries, generates optimized search queries, and performs deduplication and reranking across sources to return the most relevant documents. This function also includes a default capability to synthesize grounded natural-language answers based on the retrieved documents.
https://docs.databricks.com/aws/en/release-notes/product/2026/august#ai_search-function-beta
Related releases
- Databricks Unity AI Gateway Now Generally Available Databricks Release Notes ·
- Databricks Delta Lake Sharing with Iceberg Reads Reaches GA Databricks Release Notes ·
- Genie One now available in Databricks Excel Add-in for natural language queries Databricks Release Notes ·
- Databricks Adds Search and Replace for Files in Git Folders Databricks Release Notes ·
- Databricks-managed MCP Connectors Integrate with Unity AI Gateway (Beta) Databricks Release Notes ·
- Lakebase Now Available for Databricks Workspaces with Compliance Security Profiles Databricks Release Notes ·